Lesson 3

Measures of Central Tendency

INTRODUCTION:
Statistical methods are needed for summarizing and describing gathered
numerical data. However, by looking at the tables and graphs, one can have a
difficulty in describing the entire set of data. Better, if we can pick or choose a
single score that would represent the entirety of the data set. This value will be
helpful in making decisions based on the data collected. The measures of
central tendency are used to select the central value that could represent the
entire set of data. Thus, helping the investigator in decision making.

OBJECTIVES:
At the end of this lesson, you should be able to:
1. Describe the uses of the measures of central tendency;
2. Compute and interpret the mean, median and mode; and
3. Discuss the properties of mean, median and mode.

The Mean
The mean is the arithmetic average of the all the scores in the data set.
This is the most frequently used measure of central tendency. This is used when
the data is either interval or ratio.
The symbol x̄ read as “x bar” is used to represent sample mean while μ
read as “mu” represents the population mean.

Properties of Mean
 The most reliable measure of central tendency.
 Used when the data is interval or ratio.
 It is the layman’s concept of the average.
 All observations are considered in its computation.
 It is markedly affected by extreme values
 Used when the distribution is normal or is not badly skewed.

The Mean of ungrouped data

The mean of ungrouped data can be determined by adding the all the
scores or data and divide the sum by the numbers of scores in the data. In
symbol,
n

x 1 + x 2 + x 3 +. ..+ x n
∑ xi
i=1
x̄= or
n n

Example 1. Find the mean of 5, 7, 9 10, 12 and 15.

Solution:
 5+7+ 9+ 10+12+15 58
x̄= = =9 .67
6 6

The Mean Using MS Excel

Step 1. Open your MS Excel program.
Step 2. Type in your data.
Step 3. Select the box where you want to put the mean.
Step 4. Type the formula.
=AVERAGE(range of your data)
Step 5. Press “Enter”

You will get mean equals 9.666667 which yields the same result.

Example 2. Aling Nilda is a “kuron” vendor. In a week she earned in her

business the following amount 450, 525, 300, 740, 675, 800 and 270. Find the
mean sale of Aling Nilda in a week.

Solution:
450 + 525 + 300 + 740+ 675+ 800 + 270 3760
x̄= = =537 . 14
7 7
This means that Aling Nilda has an average earning of Php 537.14 in a week,

The Weighted Mean

There are times that a number has a certain weight. For example, you
are asked to determine your mean grade in the first semester. Given the fact
that every course (subject) has a weight, this can be done by getting the sum of
the products of a number and its weight divided by the total weight.
Suppose, x1, x2, x3 , … , xn are the scores and their respective weights are
w1, w2, w3, … , wn, the weighted mean of the scores is defined as

x 1 w1 + x2 w2 + x 3 w3 +.. .+ x n w n
x̄=
w1 + w2 +w 3 +. ..+ wn

Example 3. John’s grades last semester are as follow:

Subject Grade (x) Unit(w)

Calculus 1.5 5
Filipino 2.0 3
34
 Statistics 1.8 3
P.E. 1.3 2
NSTP 1.0 0

What is the weighted average of John’s grades last semester?

Solution:

In the given data, grades are the scores and units are the weights. To
find the weighted mean of John’s grade, the computation will be as follows:

(1 .5 )(5)+(2. 0 )(3)+(1 . 8)(3 )+(1 .3 )(2)+(1. 0 )(0) 21 .5

x̄= = =1 . 65
5+3+3+ 2+ 0 13

Therefore, John acquired an average grade of 1.65 last semester.

Weighted Mean Using MS Excel

Step 1. Open your MS Excel program.

Step 2. Type in your data.
Step 3. Name the next column as xw.

Step 4. Drag the bottom right corner up to the last row.

Step 5. Compute the total of w and xw columns.

(a) Highlight the entries.
(b) Click “Autosum” button.

35
Step 6. The weighted mean is the sum of xw divided by the sum of x.

The result is 1.65 which is the same as the computations above.

The Mean of Grouped Data

If the data is organized already and contains class intervals and
frequencies, there will be two methods that we might use in solving for the
mean– the midpoint method and the deviation method.

x̄=
∑ f i xi
The formula for midpoint method is given as: N
where: fi – frequency
xi – midpoint
N – number of cases

while the formula using deviation method will be:

x̄= A . M .+ [ ∑ f i di
N ] i

where: A.M. – assumed mean

fi – frequency of the ith class
di – deviation from the mean of the ith class
N – number of cases
i – size of the class interval

Example 4. Suppose, we will be computing the mean of the data below.

Class Intervals F
90 - 94 5
85 - 89 7
80 - 84 10
75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3

36
Solution

Method 1. Midpoint Method

Step 1. Construct midpoint column (xm). The midpoint of every class interval is
LL+UL
x m=
2 . The easier way is to start at the bottom or in the upper class
interval. Suppose you started in the highest class interval, that is
90+ 94
x m= =92
2 , subtract i = 5, to get the midpoint of the next class interval.

Class
f xm
Intervals
9 9 9
- 5
0 4 2
8 8 8
- 7
5 9 7
8 8 8
- 10
0 4 2
7 7 7
- 15
5 9 7
7 7 7
- 10
0 4 2
6 6 6
- 5
5 9 7
6 6 6
- 3
0 4 2

Step 2. Construct fxm column. The symbol fxm means we have to multiply f
column and xm column. In the highest class interval 90 – 94, f = 5 and x m = 92.
fxm = (5)(92) = 460. Do it in all class intervals.
Class
f xm fxm
Intervals
90 - 94 5 92 460
85 - 89 7 87 609
80 - 84 10 82 820
75 - 79 15 77 1155
70 - 74 10 72 720
65 - 69 5 67 335
60 - 64 3 62 186
i=5 N = 55 fxm = 4285

Step 3. Solve the size of the class interval (i), N = f , fxm, write the answer
on the bottom of their respective columns.
Class
f xm fxm
Intervals
90 - 94 5 92 460
85 - 89 7 87 609
80 - 84 10 82 820
75 - 79 15 77 1155
70 - 74 10 72 720
65 - 69 5 67 335
37
 60 - 64 3 62 186
i=5 N = 55 fxm = 4285

Step 4. Substitute the values in the formula.

x̄=
∑ fx m = 4285 =77 . 91
N 55
Method 2. Deviation Method
Step 1. Select a particular class interval and determine the assumed mean
(A.M.). Assumed mean is just the midpoint of that class interval. Suppose, we
75+79
A . M .= =77
select 75 – 79, its assumed mean is 2
Class
F
Intervals
90 - 94 5
85 - 89 7
80 - 84 10
A.M. = 77 75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3
Step 2. Construct deviation from the mean column (d column). In the row
where A.M. is located, the deviation from the mean (d column) is 0. Above it are
the positive integers starting 1 and it continues until the last row above. Below
are the negative integers starting -1 and it continues up to the last row in the
bottom.
Class
f d
Intervals
90 - 94 5 3
85 - 89 7 2
80 - 84 10 1
A.M. = 77 75 - 79 15 0
70 - 74 10 -1
65 - 69 5 -2
60 - 64 3 -3
Step 3. Construct fd column. fd means we have to multiply f and d column.
For example, class interval 65 – 69, f = 5 and d = - 2, fd = (5)(-2) = -10. Do it
in all rows.
Class
f d fd
Intervals
9 9
- 5 3 15
0 4
8 8
- 7 2 14
5 9
8 8
- 10 1 10
A.M. = 77 0 4
7 7
- 15 0 0
5 9
7 7
- 10 -1 -10
0 4
6 6
- 5 -2 -10
5 9
6 6
- 3 -3 -9
0 4
38
Step 4. Solve for i, N and fd.
Class
f d fd
Intervals
90 - 94 5 3 15
85 - 89 7 2 14
80 - 84 10 1 10
A.M. = 77 75 - 79 15 0 0
70 - 74 10 -1 -10
65 - 69 5 -2 -10
60 - 64 3 -3 -9
i=5 N = 55 fd=10

Step 5. Substitute the values in the formula.

x̄= A . M .+ [ ]
∑ fd
N
i

x̄=77+
[ ]10
55
(5 )
=77 +0 . 91

=77 . 91

Example 5. The ages of those who were inoculated with Covid 19 vaccine are
given below. Compute the mean age of the 100 people who were vaccinated.
Use any method.

Age f
60 – 66 5
53 – 59 10
46 – 52 25
39 – 45 30
32 – 38 20
25 – 31 5
18 – 24 5

Solution:

Suppose we will be using the Deviation Method. The suggestive table would be
the following:

Age (x) f d fd
60 – 66 5 3 15
53 – 59 10 2 20
46 – 52 25 1 25
A.M. = 42 39 – 45 30 0 0
32 – 38 20 -1 -20
25 – 31 5 -2 -10
18 – 24 5 -3 -15
i=7 100 15

39
 x̄= A . M .+ [ ]
∑ fd
N
i

x̄=42+ (15100 )(7 )

x̄=42+1. 05
x̄=43. 05
Therefore, the mean age of those who were vaccinated is 43.05.

The Median
Median is the middle most score in the distribution. It divides the
distribution into upper 50% and lower 50%. The determination of median
necessitates the arrangement of scores either ascending or descending. If the
number of scores (n) is odd, the median is the middle value. If n is even, the
median of the distribution is the average of two middle scores in the ordered
list. There are varieties of symbols for median. Some of the symbols are Md,
~
Mdn, Med or x . For the sake of this module, we will be using Mdn for one
simple reason – it is suggested by American Psychological Association (APA).

Characteristics of the median

 middlemost score or observation in an array
 it is not affected by extreme values
 is not amenable to algebraic manipulation
 when the distribution is grossly asymmetrical or skewed
 in an open-ended distribution, the median is the most reliable measure
of central tendency
 it is used when the data is ordinal

Median of Ungrouped Data

To determine the median of ungrouped data, we must take these steps:
Step 1. Arrange the data set in ascending or descending order.
Step 2. If n is
(a) odd, the median is the middle most value in an ordered values
(b) even, the median is the average of two middle most values

To make it easier to find the position of median in an ordered set of values the
following formula is used:
n+1
Position of Median = 2 (where n is the number of scores)
Let us try to find the median of the following distributions:

1. 4, 6, 2, 8, 10, 7, 8, 9, 9, 3, 5

Solution:
Step 1. Arrange the scores.
2, 3, 4, 5, 6, 7, 8, 8, 9, 9, 10
Step 2. Select the middlemost score. Since there are 11 scores, the position of
median is

40
 11+1 12
= =6
Position of median = 2 2 implies that the position of median is in
the 6th rank.
2, 3, 4, 5, 6, 7, 8, 8, 9, 9, 10

6th

Step 3. Identify the median in the data set.

Mdn = 7

2. 4, 16, 13, 20, 40, 35, 19, 10, 25, 40

Solution:
Step 1. Arrange the scores.
4, 10 13, 16, 19, 20, 25, 35, 40, 40

Step 2. Select the middlemost score. Since there are 10 scores, the position of
median is
10+1 11
= =5. 5
Position of median = 2 2 implies that the position of median is in
the 5.5th rank.

4, 10 13, 16, 19, 20, 25, 35, 40, 40

 
5th 6th

5.5th
Step 3. Identify the median in the data set.

19+ 20 39
Mdn= = =19 . 5
2 2

Median of Ungrouped Data with Excel

To find the median of ungrouped data using excel, these are the steps:
Step 1. Open MS Excel.
Step 2. Type in your data. Suppose, the data is give below.
Step 3. Select the box where you will be placing your answer.
Step 4. Type “=median(data range)”
Step 5. Press “Enter”

41
The result is 7. This is equal to the median of the same data set but solved
manually.

Median of Grouped Data

To find the median of grouped data, the following formula will be used:

[ ]
N
−Cf b
2
Mdn=LB+ i
f mdn
Where: LB – lower boundary of the median class
N – sample size (number of cases)
Cfb – cumulative frequency before the median class
fmdn – frequency of the median class
i – size of the class interval
Suppose we have to find the median of the following data.
Class Intervals f
90 - 94 5
85 - 89 7
80 - 84 10
75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3

Solution:

Step 1. Construct the cumulative frequency column.

(a) Start at the bottom. Copy the first entry in f column.

Class Intervals F Cf
90 - 94 5
85 - 89 7
80 - 84 10 Copy the entry
42
 75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3 3

(b) Complete Cf column upward by adding the next entry of f.

Class Intervals F Cf
90 - 94 5 Add: 5 + 3 = 8. Put it
85 - 89 7 in the Cf of the next
80 - 84 10 class step. Continue
75 - 79 15
the process until you
70 - 74 10
5 reach the top.
65 - 69 8
60 - 64 3 3

To continue:
Class Intervals f Cf
90 - 94 5 Add: 10 + 8 = 18. Put
85 - 89 7 it in the Cf of the next
80 - 84 10 class step. Continue
75 - 79 15 the process until you
70 - 74 10 18 reach the top.
65 - 69 5 8
60 - 64 3 3

Here are the complete entries for Cf column:

Class Intervals f Cf
90 - 94 5 55
85 - 89 7 50
80 - 84 10 43
75 - 79 15 33
70 - 74 10 18
65 - 69 5 8
60 - 64 3 3

Step 2. Determine i and N.

Class Intervals f Cf
90 - 94 5 55
85 - 89 7 50
80 - 84 10 43
75 - 79 15 33
70 - 74 10 18
65 - 69 5 8
60 - 64 3 3
i=5 N = 55
43
Step 3. Determine the median class.
N 55
=27 .5
(a) Compute : 2 2
N
(b) Locate the position of 2 in Cf column. Remember that cumulative
frequency is the sum of the number of cases in that class and the
number of cases of the classes below it. Thus, we can interpret Cf as
ranks. Suppose, we will take 18 in Cf column. Eighteen (18) is the sum
of 10 (no. of cases of 70 – 74 class) and 5 and 3 (no. of cases of the
classes 65 – 69 and 60 – 64, respectively).
Class Intervals f Cf
90 - 94 5 55
85 - 89 7 50
80 - 84 10 43
75 - 79 15 33
70 - 74 10 18
65 - 69 5 8 18 is the sum of
60 - 64 3 3 10 and 5 and 3.
i=5 N = 55

Another way to interpret 18 is that the ranks 9th, 10th up to 18th lie in the class
N 55
= =27 . 5 th
70 – 74. Therefore, the median class is the class containing 2 2
rank.
Class Intervals f Cf
90 - 94 5 55
85 - 89 7 50 This is the median
80 - 84 10 43 class because 19th,
75 - 79 15 33 20th up to 33rd rank is
70 - 74 10 18 here. This includes
65 - 69 5 8 the 27.5th rank.
60 - 64 3 3
i=5 N = 55
Step 3. Determine LB, fmdn, Cfb.

Class Intervals f Cf
90 - 94 5 55
85 - 89 7 50
80 - 84 10 43
LB = 74.5 75 - 79 15 33
70 - 74 10 18
65 - 69 5 8
60 - 64 3 3
i=5 N = 55
Cfb
Step 4. Substitute the values in the formula: fmdn

44
 [ ]
N
−Cf b
2
Mdn=LB+ i
f mdn

[ ]
55
−18
2
Mdn=74 .5+ (5)
15
Mdn=74 .5+3 . 17=77 .67

The Mode
The mode is the mode frequent score appearing in the distribution. It is
used when the data is nominal. If the data set is not too large, one can
determine the modal score by mere inspection. The same as mean and median,
mode has a variety of symbols. The most common are x^ and Mo. For the sake
of this module, we will be using Mo as symbol for mode.
If there is only one mode, the distribution is unimodal. If there are two
modes, the distribution is bimodal. If there are three modes, the distribution is
trimodal. If there are four or more modes, the distribution is multimodal or
polymodal. If there is no mode, the distribution is called rectangular
distribution.

Properties of Mode
 reflects the most typical value
 always located at the peak of the distribution
 not unduly affected by extreme values
 very unstable value
 the most appropriate measure of central tendency if the data is
nominal

Mode of Ungrouped Data

The mode of ungrouped data is a value or values that occur most
frequent. This can be done by mere inspection. For example, we are going to
find the mode of the following scores.
(a) 3, 4, 6, 7, 7, 7, 8, 8, 9, 10 - the mode is 7.
(b) 10, 9, 15, 10, 8, 11, 7, 12, 11, 20, 11, 5, 10 - the modes are 10 and
11.
Mode of Ungrouped Data Using MS Excel

To find the mode of ungrouped data using MS Excel, follow the following
steps:
Step 1. Open MS Excel.
Step 2. Type in your data. Suppose, the data is give below.
Step 3. Select the box where you will be placing your answer.
Step 4. Type “=Mode(data range)”
Step 5. Press “Enter”

45
The answer is 7. This is the same as the computation above. However, MS Excel
only give one answer. In case the distribution is multimodal, the program will
give you only one mode which comes first among the entries.

Mode of grouped data. The mode of grouped data can be determined

using the formula below:

Mo=LB +
[
f mo −f 1
2f mo −f 1−f 2
i
]
where: Mo - mode
LB - lower boundary of the modal class
fmo - frequency of the modal class
f1 - frequency before the modal class
f2 - frequency after the modal class

Suppose we have to find the mode of the data given previously.

Class Intervals f
90 - 94 5
85 - 89 7
80 - 84 10
75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3

Solution:

46
Step 1. Determine the modal class. The modal class is the class containing the
highest frequency.
Class Intervals f
90 - 94 5
85 - 89 7
80 - 84 10
75 - 79 15
70 - 74 10
65 - 69 5
60 - 64 3

Step 2. Determine the LB, fmo, f1, f2, and i.

Class
Intervals f
90 - 94 5
85 - 89 7
80 - 84 10 f2
LB = 74.5 75 - 79 15 fmo
70 - 74 10 f1
65 - 69 5
60 - 64 3
N=5
i=5 5

Step 3. Substitute in the formula.

Mo=LB +
[ f mo −f 1
2f mo −f 1−f 2 ] i

Mo=74 . 5+
[
15−10
2(15 )−10−10
(5 )
]
Mo=74 . 5+
[ ]
5
10
(5 )=74 . 5+2. 5
Mo=77

47